# PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph Drawing

arXiv: https://arxiv.org/abs/2606.02010 · HTML: https://mlsanity.com/paper/2606.02010/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 2 of its 20 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 2 of 2)

- [Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?](https://mlsanity.com/paper/2402.07140/) (2024)
- [Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring](https://mlsanity.com/paper/2502.07087/) (2025)

## Built on by (most cited first, 1 of 1)

- [Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models](https://mlsanity.com/paper/2608.30751/) (2026)

## Abstract (arXiv)

Existing LLM graph benchmarks typically ask models to answer graph-theoretic questions or compute symbolic solutions rather than construct spatial layouts. Within-task difficulty is also primarily stratified by vertex count. However, existing research also suggests that task difficulty is more closely related to the number of constraints imposed by the edges than to the number of vertices being arranged. We introduce PlanarBench, a benchmark that asks models to produce crossing-free ASCII drawings of planar graphs given only an edge list. Across 91 model configurations and 199 non-isomorphic connected planar graphs with 2-7 vertices, edge count is more strongly associated with mean task score than vertex count (r=-0.85) versus (r=-0.47) and remains strongly associated after controlling for vertex count (rp=-0.80). PlanarBench provides a controlled setting for separating these two difficulty axes. In addition, neither drawing area nor total response length demonstrated a meaningful correlation with score, which is evidence against a simple output-size explanation. Performance varies widely: the best model scores 159.5 out of 199, most models below 30B parameters score under 25, and substantial failures remain among frontier systems.